Triple

T10850805
Position Surface form Disambiguated ID Type / Status
Subject Ray Davies E256136 entity
Predicate notableWork P4 FINISHED
Object Come Dancing E794455 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Come Dancing | Statement: [Ray Davies, notableWork, Come Dancing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Come Dancing
Context triple: [Ray Davies, notableWork, Come Dancing]
  • A. Come Dancing
    Come Dancing was a long-running British television ballroom dancing competition that showcased amateur dancers and helped popularize the genre on UK television.
  • B. Come Dancing chosen
    "Come Dancing" is a nostalgic 1982 pop song by The Kinks that reflects on lost youth and the decline of traditional dance halls.
  • C. Shall We Dance
    "Shall We Dance" is a 1937 Hollywood musical film starring Fred Astaire and Ginger Rogers, celebrated for its sophisticated dance sequences and classic George and Ira Gershwin songs.
  • D. Dance On
    "Dance On" is a politically charged funk-rock song by Prince from his 1988 album Lovesexy.
  • E. A Time for Dancing
    A Time for Dancing is a 2000 teen drama film about two best friends whose bond is tested when one of them is diagnosed with cancer.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75116af20819084c7f8fa88d18e61 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb17d978c8190883b4a56e88859de completed April 14, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:20 p.m.